Automatic text analysis: gradations of text types in web pages

M. Santini

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

Abstract

In this paper we present a first implementation of a linguistic expert system, which combines Bayesian inference and the knowledge of a domain expert, the linguist. The system is capable of automatically deriving the gradations of four text types -- descriptive/narrative, explicatory/informational, argumentative/persuasive, instructional -- from web pages. The evaluation of the system against human assessment shows that the system is effective and promising.
Original languageEnglish
Title of host publicationProceedings of the 10th ESSLLI student session
EditorsJ. Gervain
Pages276-285
Number of pages10
Publication statusPublished - 2005
EventProceedings of the 10th ESSLLI student session - Edinburgh, UK
Duration: 1 Jan 2005 → …

Conference

ConferenceProceedings of the 10th ESSLLI student session
Period1/01/05 → …

Bibliographical note

Item is freely available at: http://people.sissa.it/~gervain/ProceedingsPages145-296.pdf

Fingerprint Dive into the research topics of 'Automatic text analysis: gradations of text types in web pages'. Together they form a unique fingerprint.

  • Cite this

    Santini, M. (2005). Automatic text analysis: gradations of text types in web pages. In J. Gervain (Ed.), Proceedings of the 10th ESSLLI student session (pp. 276-285) http://people.sissa.it/~gervain/StuS.html